Coronary interventions - Mini focus on deep learning in interventional cardiology

Artificial intelligence and optical coherence tomography for the automatic characterisation of human atherosclerotic plaques

EuroIntervention 2021;17:41-50. DOI: 10.4244/EIJ-D-20-01355

Miao Chu
Miao Chu1, BSc; Haibo Jia2, MD, PhD; Juan Luis Gutiérrez-Chico3, MD, PhD; Akiko Maehara4,5, MD, PhD; Ziad A. Ali4,5, MD, DPhil; Xiaoling Zeng6, MD; Luping He2, MD; Chen Zhao2, MD; Mitsuaki Matsumura5, BS; Peng Wu1, BSc; Ming Zeng2, MD; Takashi Kubo7, MD, PhD; Bo Xu8, MBBS; Lianglong Chen6, MD, PhD; Bo Yu2, MD, PhD; Gary S. Mintz5, PhD, MD; William Wijns9, MD, PhD; Niels Ramsing Holm10, MD; Shengxian Tu1,6, PhD
1. School of Biomedical Engineering, Shanghai Jiao Tong University, Shanghai, China; 2. Department of Cardiology, 2nd Affiliated Hospital of Harbin Medical University, Harbin, China; 3. Cardiology Department, Campo de Gibraltar Health Trust, Algeciras, Spain; 4. Center for Interventional Vascular Therapy, Division of Cardiology, Presbyterian Hospital and Columbia University, New York, NY, USA; 5. Cardiovascular Research Foundation, New York, NY, USA; 6. Department of Cardiology, Fujian Medical University Union Hospital, Fuzhou, Fujian, China; 7. Department of Cardiovascular Medicine, Wakayama Medical University, Wakayama, Japan; 8. Fu Wai Hospital, National Center for Cardiovascular Diseases, Chinese Academy of Medical Sciences, Beijing, China; 9. The Lambe Institute for Translational Medicine and CURAM, National University of Ireland Galway, Galway, Ireland; 10. Department of Cardiology, Aarhus University Hospital, Aarhus, Denmark

Background: Intravascular optical coherence tomography (IVOCT) enables detailed plaque characterisation in vivo, but visual assessment is time-consuming and subjective.

Aims: This study aimed to develop and validate an automatic framework for IVOCT plaque characterisation using artificial intelligence (AI).

Methods: IVOCT pullbacks from five international centres were analysed in a core lab, annotating basic plaque components, inflammatory markers and other structures. A deep convolutional network with encoding-decoding architecture and pseudo-3D input was developed and trained using hybrid loss. The proposed network was integrated into commercial software to be externally validated on additional IVOCT pullbacks from three international core labs, taking the consensus among core labs as reference.

Results: Annotated images from 509 pullbacks (391 patients) were divided into 10,517 and 1,156 cross-sections for the training and testing data sets, respectively. The Dice coefficient of the model was 0.906 for fibrous plaque, 0.848 for calcium and 0.772 for lipid in the testing data set. Excellent agreement in plaque burden quantification was observed between the model and manual measurements (R2=0.98). In the external validation, the software correctly identified 518 out of 598 plaque regions from 300 IVOCT cross-sections, with a diagnostic accuracy of 97.6% (95% CI: 93.4-99.3%) in fibrous plaque, 90.5% (95% CI: 85.2-94.1%) in lipid and 88.5% (95% CI: 82.4-92.7%) in calcium. The median time required for analysis was 21.4 (18.6-25.0) seconds per pullback.

Conclusions: A novel AI framework for automatic plaque characterisation in IVOCT was developed, providing excellent diagnostic accuracy in both internal and external validation. This model might reduce subjectivity in image interpretation and facilitate IVOCT quantification of plaque composition, with potential applications in research and IVOCT-guided PCI.

Sign in to read and download the full article

Forgot your password?

No account yet?
Sign up for free!

Create my pcr account

Join us for free and access thousands of articles from EuroIntervention, as well as presentations, videos, cases from

optical coherence tomographyintravascular ultrasoundstable angina
Coronary interventionsStable CAD
Read next article
Deep learning for prediction of fractional flow reserve from resting coronary pressure curves

Latest news